| { |
| "architectures": [ |
| "SLModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token": "<|begin_of_text|>", |
| "bos_token_id": 128000, |
| "eos_token": "<|end_of_text|>", |
| "eos_token_id": 128001, |
| "pad_token": "<|end_of_text|>", |
| "pad_token_id": 128001, |
| "mask_token": "<|mask|>", |
| "mask_token_id": 128002, |
| "hidden_act": "silu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 2048, |
| "model_type": "sl_model", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 12, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.40.0.dev0", |
| "use_cache": true, |
| "vocab_size": 128256, |
| "is_causal": false, |
| "auto_map": { |
| "AutoConfig": "configuration_sl_model.SLModelConfig", |
| "AutoModel": "modeling_sl_model.SLModel", |
| "AutoModelForPreTraining": "modeling_sl_model.SLPreTrainedModel", |
| "AutoModelForSequenceClassification": "modeling_sl_model.SLModelForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_sl_model.SLModelForTokenClassification" |
| } |
| } |
